Catalog
BerriAI/add-agent

BerriAI

add-agent

Create a new AI agent on a live LiteLLM proxy. Asks for agent name, the underlying model, and optional MCP server access, then calls POST /v1/agents.

v1.0LATEST
NewUpdated Oct 12, 2026

Add Agent

Create a new AI agent on a live LiteLLM proxy.

Setup

Ask for these if not already known:

LITELLM_BASE_URL  — e.g. https://my-proxy.example.com
LITELLM_API_KEY   — proxy admin key

API reference: https://docs.litellm.ai/docs/proxy/agents

Ask the user

  1. Agent name (required, e.g. my-coding-agent)
  2. Model — which LiteLLM model should this agent use (e.g. gpt-4o, claude-3-5-sonnet)
  3. Description (optional, shown to callers)
  4. MCP servers (optional) — list of server_ids this agent can use

Run

curl -s -X POST "$BASE/v1/agents" \
  -H "Authorization: Bearer $KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "agent_name": "<name>",
    "litellm_params": {
      "model": "<model>"
    },
    "agent_card_params": {
      "name": "<name>",
      "description": "<description>",
      "version": "1.0"
    }
  }'

List existing agents

curl -s "$BASE/v1/agents" \
  -H "Authorization: Bearer $KEY"

Get agent info

curl -s "$BASE/v1/agents/<agent_id>" \
  -H "Authorization: Bearer $KEY"

Delete an agent

curl -s -X DELETE "$BASE/v1/agents/<agent_id>" \
  -H "Authorization: Bearer $KEY"

Output

Show agent_id — needed to call or delete this agent later.

Files1
1 files · 1.0 KB

Select a file to preview

Overall Score

72/100

Grade

B

Good

Grades are signals, not a certification. Always review a skill yourself before use.

Safety

70

Quality

72

Clarity

78

Completeness

66

Summary

This skill guides an AI agent to create a new AI agent on a live LiteLLM proxy by collecting configuration details (name, model, description, MCP servers) and making a POST request to the proxy's /v1/agents endpoint. It also documents how to list, retrieve, and delete agents using curl.

Detected Capabilities

http-requestshell-executioncredential-inputenvironment-variable-read

Trigger Keywords

Phrases that agents use to match this skill to user intent.

create litellm agentconfigure proxy agentadd mcp serverdeploy agent modellitellm agent setup

Risk Signals

WARNING

API key passed via command-line environment variable in curl request

Run section, curl command with -H Authorization header
WARNING

Proxy URL and API key must be provided by user without documented validation

Setup section
INFO

No error handling documented for failed requests or invalid configuration

Run section

Referenced Domains

External domains referenced in skill content, detected by static analysis.

docs.litellm.aimy-proxy.example.com

Use Cases

  • Create a new AI agent on a LiteLLM proxy for coding tasks
  • Configure agent model and MCP server permissions
  • Retrieve created agent ID for later invocation
  • List all agents currently running on a proxy
  • Delete an agent from a LiteLLM deployment
  • Query agent configuration details

Quality Notes

  • Skill clearly scopes its purpose to agent creation on LiteLLM proxies
  • Practical setup instructions ask for required credentials upfront
  • Includes related operations (list, get, delete) for context and agent management workflow
  • API reference link provided for additional documentation
  • Missing: error handling patterns (e.g., what to do if API key is invalid or endpoint unreachable)
  • Missing: validation guidance for agent name, model, and MCP server IDs
  • Missing: example curl responses showing expected JSON structure
  • Missing: security note about protecting API keys from logs/history
Model: claude-haiku-4-5-20251001Analyzed: Oct 12, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

Use BerriAI/add-agent in your dev environment

Command Palette

Search for a command to run...